birdnet-analyzer 2.0.0__py3-none-any.whl → 2.0.1__py3-none-any.whl

birdnet_analyzer/evaluation/preprocessing/utils.py

@@ -0,0 +1,98 @@
+"""
+Utility Functions for Data Processing Tasks
+
+This module provides helper functions to handle common data processing tasks, such as:
+- Extracting recording filenames from file paths or filenames.
+- Reading and concatenating text files from a specified directory.
+
+It is designed to work seamlessly with pandas and file system operations.
+"""
+
+import os
+
+import pandas as pd
+
+
+def extract_recording_filename(path_column: pd.Series) -> pd.Series:
+    """
+    Extract the recording filename from a path column.
+
+    This function processes a pandas Series containing file paths and extracts the base filename
+    (without the extension) for each path.
+
+    Args:
+        path_column (pd.Series): A pandas Series containing file paths.
+
+    Returns:
+        pd.Series: A pandas Series containing the extracted recording filenames.
+    """
+    # Apply a lambda function to extract the base filename without extension
+    return path_column.apply(lambda x: os.path.splitext(os.path.basename(x))[0] if isinstance(x, str) else x)
+
+
+def extract_recording_filename_from_filename(filename_series: pd.Series) -> pd.Series:
+    """
+    Extract the recording filename from a filename Series.
+
+    This function processes a pandas Series containing filenames and extracts the base filename
+    (without the extension) for each.
+
+    Args:
+        filename_series (pd.Series): A pandas Series containing filenames.
+
+    Returns:
+        pd.Series: A pandas Series containing the extracted recording filenames.
+    """
+    # Apply a lambda function to split filenames and remove the extension
+    return filename_series.apply(lambda x: x.split(".")[0] if isinstance(x, str) else x)
+
+
+def read_and_concatenate_files_in_directory(directory_path: str) -> pd.DataFrame:
+    """
+    Read and concatenate all .txt files in a directory into a single DataFrame.
+
+    This function scans the specified directory for all .txt files, reads each file into a DataFrame,
+    appends a 'source_file' column containing the filename, and concatenates all DataFrames into one.
+    If the files have inconsistent columns, a ValueError is raised.
+
+    Args:
+        directory_path (str): Path to the directory containing the .txt files.
+
+    Returns:
+        pd.DataFrame: A concatenated DataFrame containing the data from all .txt files,
+        or an empty DataFrame if no files are found.
+
+    Raises:
+        ValueError: If the columns in the files are inconsistent.
+    """
+    df_list: list[pd.DataFrame] = []  # List to hold individual DataFrames
+    columns_set = None  # To ensure consistency in column names
+
+    # Iterate through each file in the directory
+    for filename in sorted(os.listdir(directory_path)):
+        if filename.endswith(".txt"):
+            filepath = os.path.join(directory_path, filename)  # Construct the full file path
+
+            try:
+                # Attempt to read the file as a tab-separated values file with UTF-8 encoding
+                df = pd.read_csv(filepath, sep="\t", encoding="utf-8")
+            except UnicodeDecodeError:
+                # Fallback to 'latin-1' encoding if UTF-8 fails
+                df = pd.read_csv(filepath, sep="\t", encoding="latin-1")
+
+            # Check for column consistency across files
+            if columns_set is None:
+                columns_set = set(df.columns)  # Initialize with the first file's columns
+            elif set(df.columns) != columns_set:
+                raise ValueError(f"File {filename} has different columns than the previous files.")
+
+            # Add a column to indicate the source file for traceability
+            df["source_file"] = filename
+
+            # Append the DataFrame to the list
+            df_list.append(df)
+
+    # Concatenate all DataFrames if any were processed, else return an empty DataFrame
+    if df_list:
+        return pd.concat(df_list, ignore_index=True)
+    return pd.DataFrame()  # Return an empty DataFrame if no .txt files were found

birdnet_analyzer/gui/__init__.py

@@ -1,23 +1,19 @@
-def main():
-    import birdnet_analyzer.gui.multi_file as mfa
-    import birdnet_analyzer.gui.review as review
-    import birdnet_analyzer.gui.segments as gs
-    import birdnet_analyzer.gui.single_file as sfa
-    import birdnet_analyzer.gui.species as species
-    import birdnet_analyzer.gui.train as train
-    import birdnet_analyzer.gui.utils as gu
-    import birdnet_analyzer.gui.embeddings as embeddings
-    import birdnet_analyzer.gui.evaluation as evaluation
-
-    gu.open_window(
-        [
-            sfa.build_single_analysis_tab,
-            mfa.build_multi_analysis_tab,
-            train.build_train_tab,
-            gs.build_segments_tab,
-            review.build_review_tab,
-            species.build_species_tab,
-            embeddings.build_embeddings_tab,
-            evaluation.build_evaluation_tab,
-        ]
-    )
+def main():
+    import birdnet_analyzer.gui.multi_file as mfa
+    import birdnet_analyzer.gui.segments as gs
+    import birdnet_analyzer.gui.single_file as sfa
+    import birdnet_analyzer.gui.utils as gu
+    from birdnet_analyzer.gui import embeddings, evaluation, review, species, train
+
+    gu.open_window(
+        [
+            sfa.build_single_analysis_tab,
+            mfa.build_multi_analysis_tab,
+            train.build_train_tab,
+            gs.build_segments_tab,
+            review.build_review_tab,
+            species.build_species_tab,
+            embeddings.build_embeddings_tab,
+            evaluation.build_evaluation_tab,
+        ]
+    )

birdnet_analyzer/gui/__main__.py

@@ -1,3 +1,3 @@
-from birdnet_analyzer.gui import main
-
-main()
+from birdnet_analyzer.gui import main
+
+main()

birdnet_analyzer/gui/analysis.py

@@ -1,174 +1,175 @@
-import concurrent.futures
-import os
-from pathlib import Path
-
-import gradio as gr
-
-import birdnet_analyzer.config as cfg
-import birdnet_analyzer.gui.utils as gu
-import birdnet_analyzer.gui.localization as loc
-import birdnet_analyzer.model as model
-
-
-from birdnet_analyzer.analyze.utils import analyze_file, combine_results, save_analysis_params
-
-SCRIPT_DIR = os.path.abspath(os.path.dirname(__file__))
-ORIGINAL_LABELS_FILE = str(Path(SCRIPT_DIR).parent / cfg.LABELS_FILE)
-
-
-def analyze_file_wrapper(entry):
-    """
-    Wrapper function for analyzing a file.
-
-    Args:
-        entry (tuple): A tuple where the first element is the file path and the
-                       remaining elements are arguments to be passed to the
-                       analyze.analyzeFile function.
-
-    Returns:
-        tuple: A tuple where the first element is the file path and the second
-               element is the result of the analyze.analyzeFile function.
-    """
-    return (entry[0], analyze_file(entry))
-
-
-def run_analysis(
-    input_path: str,
-    output_path: str | None,
-    use_top_n: bool,
-    top_n: int,
-    confidence: float,
-    sensitivity: float,
-    overlap: float,
-    merge_consecutive: int,
-    audio_speed: float,
-    fmin: int,
-    fmax: int,
-    species_list_choice: str,
-    species_list_file,
-    lat: float,
-    lon: float,
-    week: int,
-    use_yearlong: bool,
-    sf_thresh: float,
-    custom_classifier_file,
-    output_types: str,
-    combine_tables: bool,
-    locale: str,
-    batch_size: int,
-    threads: int,
-    input_dir: str,
-    skip_existing: bool,
-    save_params: bool,
-    progress: gr.Progress | None,
-):
-    """Starts the analysis.
-
-    Args:
-        input_path: Either a file or directory.
-        output_path: The output path for the result, if None the input_path is used
-        confidence: The selected minimum confidence.
-        sensitivity: The selected sensitivity.
-        overlap: The selected segment overlap.
-        merge_consecutive: The number of consecutive segments to merge into one.
-        audio_speed: The selected audio speed.
-        fmin: The selected minimum bandpass frequency.
-        fmax: The selected maximum bandpass frequency.
-        species_list_choice: The choice for the species list.
-        species_list_file: The selected custom species list file.
-        lat: The selected latitude.
-        lon: The selected longitude.
-        week: The selected week of the year.
-        use_yearlong: Use yearlong instead of week.
-        sf_thresh: The threshold for the predicted species list.
-        custom_classifier_file: Custom classifier to be used.
-        output_type: The type of result to be generated.
-        output_filename: The filename for the combined output.
-        locale: The translation to be used.
-        batch_size: The number of samples in a batch.
-        threads: The number of threads to be used.
-        input_dir: The input directory.
-        progress: The gradio progress bar.
-    """
-    if progress is not None:
-        progress(0, desc=f"{loc.localize('progress-preparing')} ...")
-
-    from birdnet_analyzer.analyze.core import _set_params
-
-    locale = locale.lower()
-    custom_classifier = custom_classifier_file if species_list_choice == gu._CUSTOM_CLASSIFIER else None
-    slist = species_list_file if species_list_choice == gu._CUSTOM_SPECIES else None
-    lat = lat if species_list_choice == gu._PREDICT_SPECIES else -1
-    lon = lon if species_list_choice == gu._PREDICT_SPECIES else -1
-    week = -1 if use_yearlong else week
-
-    flist = _set_params(
-        input=input_dir if input_dir else input_path,
-        min_conf=confidence,
-        custom_classifier=custom_classifier,
-        sensitivity=min(1.25, max(0.75, float(sensitivity))),
-        locale=locale,
-        overlap=max(0.0, min(2.9, float(overlap))),
-        merge_consecutive=max(1, int(merge_consecutive)),
-        audio_speed=max(0.1, 1.0 / (audio_speed * -1)) if audio_speed < 0 else max(1.0, float(audio_speed)),
-        fmin=max(0, min(cfg.SIG_FMAX, int(fmin))),
-        fmax=max(cfg.SIG_FMIN, min(cfg.SIG_FMAX, int(fmax))),
-        bs=max(1, int(batch_size)),
-        combine_results=combine_tables,
-        rtype=output_types,
-        skip_existing_results=skip_existing,
-        threads=max(1, int(threads)),
-        labels_file=ORIGINAL_LABELS_FILE,
-        sf_thresh=sf_thresh,
-        lat=lat,
-        lon=lon,
-        week=week,
-        slist=slist,
-        top_n=top_n if use_top_n else None,
-        output=output_path,
-    )
-
-    if species_list_choice == gu._CUSTOM_CLASSIFIER:
-        if custom_classifier_file is None:
-            raise gr.Error(loc.localize("validation-no-custom-classifier-selected"))
-
-        model.reset_custom_classifier()
-
-    gu.validate(cfg.FILE_LIST, loc.localize("validation-no-audio-files-found"))
-
-    result_list = []
-
-    if progress is not None:
-        progress(0, desc=f"{loc.localize('progress-starting')} ...")
-
-    # Analyze files
-    if cfg.CPU_THREADS < 2:
-        for entry in flist:
-            result_list.append(analyze_file_wrapper(entry))
-    else:
-        with concurrent.futures.ProcessPoolExecutor(max_workers=cfg.CPU_THREADS) as executor:
-            futures = (executor.submit(analyze_file_wrapper, arg) for arg in flist)
-            for i, f in enumerate(concurrent.futures.as_completed(futures), start=1):
-                if progress is not None:
-                    progress((i, len(flist)), total=len(flist), unit="files")
-                result = f.result()
-
-                result_list.append(result)
-
-    # Combine results?
-    if cfg.COMBINE_RESULTS:
-        combine_list = [[r[1] for r in result_list if r[0] == i[0]][0] for i in flist]
-        print(f"Combining results, writing to {cfg.OUTPUT_PATH}...", end="", flush=True)
-        combine_results(combine_list)
-        print("done!", flush=True)
-
-    if save_params:
-        save_analysis_params(os.path.join(cfg.OUTPUT_PATH, cfg.ANALYSIS_PARAMS_FILENAME))
-
-    return (
-        [[os.path.relpath(r[0], input_dir), bool(r[1])] for r in result_list]
-        if input_dir
-        else result_list[0][1]["csv"]
-        if result_list[0][1]
-        else None
-    )
+import concurrent.futures
+import os
+from pathlib import Path
+
+import gradio as gr
+
+import birdnet_analyzer.config as cfg
+import birdnet_analyzer.gui.localization as loc
+import birdnet_analyzer.gui.utils as gu
+from birdnet_analyzer import model
+from birdnet_analyzer.analyze.utils import (
+    analyze_file,
+    combine_results,
+    save_analysis_params,
+)
+
+SCRIPT_DIR = os.path.abspath(os.path.dirname(__file__))
+ORIGINAL_LABELS_FILE = str(Path(SCRIPT_DIR).parent / cfg.LABELS_FILE)
+
+
+def analyze_file_wrapper(entry):
+    """
+    Wrapper function for analyzing a file.
+
+    Args:
+        entry (tuple): A tuple where the first element is the file path and the
+                       remaining elements are arguments to be passed to the
+                       analyze.analyzeFile function.
+
+    Returns:
+        tuple: A tuple where the first element is the file path and the second
+               element is the result of the analyze.analyzeFile function.
+    """
+    return (entry[0], analyze_file(entry))
+
+
+def run_analysis(
+    input_path: str,
+    output_path: str | None,
+    use_top_n: bool,
+    top_n: int,
+    confidence: float,
+    sensitivity: float,
+    overlap: float,
+    merge_consecutive: int,
+    audio_speed: float,
+    fmin: int,
+    fmax: int,
+    species_list_choice: str,
+    species_list_file,
+    lat: float,
+    lon: float,
+    week: int,
+    use_yearlong: bool,
+    sf_thresh: float,
+    custom_classifier_file,
+    output_types: str,
+    combine_tables: bool,
+    locale: str,
+    batch_size: int,
+    threads: int,
+    input_dir: str,
+    skip_existing: bool,
+    save_params: bool,
+    progress: gr.Progress | None,
+):
+    """Starts the analysis.
+
+    Args:
+        input_path: Either a file or directory.
+        output_path: The output path for the result, if None the input_path is used
+        confidence: The selected minimum confidence.
+        sensitivity: The selected sensitivity.
+        overlap: The selected segment overlap.
+        merge_consecutive: The number of consecutive segments to merge into one.
+        audio_speed: The selected audio speed.
+        fmin: The selected minimum bandpass frequency.
+        fmax: The selected maximum bandpass frequency.
+        species_list_choice: The choice for the species list.
+        species_list_file: The selected custom species list file.
+        lat: The selected latitude.
+        lon: The selected longitude.
+        week: The selected week of the year.
+        use_yearlong: Use yearlong instead of week.
+        sf_thresh: The threshold for the predicted species list.
+        custom_classifier_file: Custom classifier to be used.
+        output_type: The type of result to be generated.
+        output_filename: The filename for the combined output.
+        locale: The translation to be used.
+        batch_size: The number of samples in a batch.
+        threads: The number of threads to be used.
+        input_dir: The input directory.
+        progress: The gradio progress bar.
+    """
+    if progress is not None:
+        progress(0, desc=f"{loc.localize('progress-preparing')} ...")
+
+    from birdnet_analyzer.analyze.core import _set_params
+
+    locale = locale.lower()
+    custom_classifier = custom_classifier_file if species_list_choice == gu._CUSTOM_CLASSIFIER else None
+    slist = species_list_file if species_list_choice == gu._CUSTOM_SPECIES else None
+    lat = lat if species_list_choice == gu._PREDICT_SPECIES else -1
+    lon = lon if species_list_choice == gu._PREDICT_SPECIES else -1
+    week = -1 if use_yearlong else week
+
+    flist = _set_params(
+        audio_input=input_dir if input_dir else input_path,
+        min_conf=confidence,
+        custom_classifier=custom_classifier,
+        sensitivity=min(1.25, max(0.75, float(sensitivity))),
+        locale=locale,
+        overlap=max(0.0, min(2.9, float(overlap))),
+        merge_consecutive=max(1, int(merge_consecutive)),
+        audio_speed=max(0.1, 1.0 / (audio_speed * -1)) if audio_speed < 0 else max(1.0, float(audio_speed)),
+        fmin=max(0, min(cfg.SIG_FMAX, int(fmin))),
+        fmax=max(cfg.SIG_FMIN, min(cfg.SIG_FMAX, int(fmax))),
+        bs=max(1, int(batch_size)),
+        combine_results=combine_tables,
+        rtype=output_types,
+        skip_existing_results=skip_existing,
+        threads=max(1, int(threads)),
+        labels_file=ORIGINAL_LABELS_FILE,
+        sf_thresh=sf_thresh,
+        lat=lat,
+        lon=lon,
+        week=week,
+        slist=slist,
+        top_n=top_n if use_top_n else None,
+        output=output_path,
+    )
+
+    if species_list_choice == gu._CUSTOM_CLASSIFIER:
+        if custom_classifier_file is None:
+            raise gr.Error(loc.localize("validation-no-custom-classifier-selected"))
+
+        model.reset_custom_classifier()
+
+    gu.validate(cfg.FILE_LIST, loc.localize("validation-no-audio-files-found"))
+
+    result_list = []
+
+    if progress is not None:
+        progress(0, desc=f"{loc.localize('progress-starting')} ...")
+
+    # Analyze files
+    if cfg.CPU_THREADS < 2:
+        result_list.extend(analyze_file_wrapper(entry) for entry in flist)
+    else:
+        with concurrent.futures.ProcessPoolExecutor(max_workers=cfg.CPU_THREADS) as executor:
+            futures = (executor.submit(analyze_file_wrapper, arg) for arg in flist)
+            for i, f in enumerate(concurrent.futures.as_completed(futures), start=1):
+                if progress is not None:
+                    progress((i, len(flist)), total=len(flist), unit="files")
+                result = f.result()
+
+                result_list.append(result)
+
+    # Combine results?
+    if cfg.COMBINE_RESULTS:
+        combine_list = [[r[1] for r in result_list if r[0] == i[0]][0] for i in flist]
+        print(f"Combining results, writing to {cfg.OUTPUT_PATH}...", end="", flush=True)
+        combine_results(combine_list)
+        print("done!", flush=True)
+
+    if save_params:
+        save_analysis_params(os.path.join(cfg.OUTPUT_PATH, cfg.ANALYSIS_PARAMS_FILENAME))
+
+    return (
+        [[os.path.relpath(r[0], input_dir), bool(r[1])] for r in result_list]
+        if input_dir
+        else result_list[0][1]["csv"]
+        if result_list[0][1]
+        else None
+    )

birdnet_analyzer/gui/assets/arrow_down.svg

@@ -1,4 +1,4 @@
-<svg width="50" height="50" viewBox="0 0 50 50" xmlns="http://www.w3.org/2000/svg">
-  <rect x="5" y="5" width="40" height="40" rx="5" ry="5" fill="#ccc" stroke="#888" stroke-width="2"/>
-  <polygon points="25,36 12,24 20,24 20,16 30,16 30,24 38,24" fill="black"/>
-</svg>
+<svg width="50" height="50" viewBox="0 0 50 50" xmlns="http://www.w3.org/2000/svg">
+  <rect x="5" y="5" width="40" height="40" rx="5" ry="5" fill="#ccc" stroke="#888" stroke-width="2"/>
+  <polygon points="25,36 12,24 20,24 20,16 30,16 30,24 38,24" fill="black"/>
+</svg>

birdnet_analyzer/gui/assets/arrow_left.svg

@@ -1,4 +1,4 @@
-<svg width="50" height="50" viewBox="0 0 50 50" xmlns="http://www.w3.org/2000/svg">
-  <rect x="5" y="5" width="40" height="40" rx="5" ry="5" fill="#ccc" stroke="#888" stroke-width="2"/>
-  <polygon points="14,25 26,12 26,20 34,20 34,30 26,30 26,38" fill="black"/>
-</svg>
+<svg width="50" height="50" viewBox="0 0 50 50" xmlns="http://www.w3.org/2000/svg">
+  <rect x="5" y="5" width="40" height="40" rx="5" ry="5" fill="#ccc" stroke="#888" stroke-width="2"/>
+  <polygon points="14,25 26,12 26,20 34,20 34,30 26,30 26,38" fill="black"/>
+</svg>

birdnet_analyzer/gui/assets/arrow_right.svg

@@ -1,4 +1,4 @@
-<svg width="50" height="50" viewBox="0 0 50 50" xmlns="http://www.w3.org/2000/svg">
-  <rect x="5" y="5" width="40" height="40" rx="5" ry="5" fill="#ccc" stroke="#888" stroke-width="2"/>
-  <polygon points="36,25 24,12 24,20 16,20 16,30 24,30 24,38" fill="black"/>
-</svg>
+<svg width="50" height="50" viewBox="0 0 50 50" xmlns="http://www.w3.org/2000/svg">
+  <rect x="5" y="5" width="40" height="40" rx="5" ry="5" fill="#ccc" stroke="#888" stroke-width="2"/>
+  <polygon points="36,25 24,12 24,20 16,20 16,30 24,30 24,38" fill="black"/>
+</svg>

birdnet_analyzer/gui/assets/arrow_up.svg

@@ -1,4 +1,4 @@
-<svg width="50" height="50" viewBox="0 0 50 50" xmlns="http://www.w3.org/2000/svg">
-  <rect x="5" y="5" width="40" height="40" rx="5" ry="5" fill="#ccc" stroke="#888" stroke-width="2"/>
-  <polygon points="25,14 12,26 20,26 20,34 30,34 30,26 38,26" fill="black"/>
-</svg>
+<svg width="50" height="50" viewBox="0 0 50 50" xmlns="http://www.w3.org/2000/svg">
+  <rect x="5" y="5" width="40" height="40" rx="5" ry="5" fill="#ccc" stroke="#888" stroke-width="2"/>
+  <polygon points="25,14 12,26 20,26 20,34 30,34 30,26 38,26" fill="black"/>
+</svg>

birdnet_analyzer/gui/assets/gui.css

@@ -1,29 +1,29 @@
-footer {
-    display: none !important;
-}
-
-#single_file_audio,
-#single_file_audio * {
-    max-height: 81.6px;
-    min-height: 0;
-}
-
-#update-available a {
-    text-decoration: none;
-}
-
-:root {
-    --block-title-text-color: var(--neutral-800);
-    --block-info-text-color: var(--neutral-500);
-}
-
-#single-file-output td:first-of-type span {
-    text-align: center;
-}
-
-#embeddings-search-results {
-    max-height: 1107px;
-    overflow: auto;
-    flex-wrap: nowrap;
-    padding-right: 5px;
+footer {
+    display: none !important;
+}
+
+#single_file_audio,
+#single_file_audio * {
+    max-height: 81.6px;
+    min-height: 0;
+}
+
+#update-available a {
+    text-decoration: none;
+}
+
+:root {
+    --block-title-text-color: var(--neutral-800);
+    --block-info-text-color: var(--neutral-500);
+}
+
+#single-file-output td:first-of-type span {
+    text-align: center;
+}
+
+#embeddings-search-results {
+    max-height: 1107px;
+    overflow: auto;
+    flex-wrap: nowrap;
+    padding-right: 5px;
 }